Code Wiki
Trigger a one-shot workflow that clones (or pulls) a Git repository, generates a structured wiki from it using the `codewiki` CLI, and optionally renders the...
jiangsier-xyz
@jiangsier-xyz
What This Skill Does
Clones or pulls a Git repository and generates a structured wiki from its codebase using the codewiki CLI, with optional rendering into static documentation sites (MkDocs or VitePress) and an HTTP preview server.
Replaces manually writing and maintaining project documentation by automatically extracting code structure and generating a navigable wiki from any Git repository.
When to Use It
- Generate a structured wiki for a GitHub repository like 'anthropics/claude-code'
- Create MkDocs or VitePress documentation site from a codebase with one command
- Preview generated documentation locally with a live HTTP server
- Document a private repository by providing its Git URL or SSH path
- Add custom focus instructions to tailor the wiki content for specific audiences
Install
$ openclaw skills install @jiangsier-xyz/codewikiSkill: Code Wiki
When to trigger
Invoke this skill when the user:
- Types
/codewiki <input>, or - Asks in natural language to generate a wiki / documentation from a repository (e.g. "generate a wiki for anthropics/claude-code").
Trigger command
/codewiki <user_input>
Dependencies
This skill depends on CodeWiki
(FSoft-AI4Code/CodeWiki). The codewiki CLI — provided by that project —
must be installed and available on $PATH before the underlying script can
run. The script's startup check_dependencies step will fail with exit code
2 and a clear message if codewiki is missing.
If the user has not installed CodeWiki yet, direct them to https://github.com/FSoft-AI4Code/CodeWiki and have them follow the install instructions there before confirming execution.
When the user requests rendering (--render), two additional host tools are
required: python3 (MkDocs) and node + npm (VitePress). The
per-renderer dependencies are installed automatically into isolated
sandboxes (Python venv / private node_modules) at render time, so the user
never needs to run pip install or npm install manually. If either host
tool is missing, render_docs.sh exits with a friendly install hint.
Agent execution logic
Follow these steps in order. Do not execute the underlying script until the user has explicitly confirmed.
1. Parse <user_input>
Extract five fields from the user's input. Accept natural-language phrasing and shorthand.
| Field | Required | Accepted forms | Default |
|---|---|---|---|
| repository | yes | group/repo, https://github.com/..., git@github.com:... | — |
| output dir | no | any local path | . |
| instructions | no | free-form text describing focus / constraints | (none) |
| render stack | no | mkdocs, vitepress, both, or "skip" | skip |
| serve | no | boolean, optionally with a port number | off |
Detection heuristics:
- repository: the first token matching
^\w[\w.-]*/[\w.-]+$, or starting withhttps://orgit@. - output dir: a token following words like
into,to,under,at, or a path-looking token (./,/, or containing/). - instructions: everything remaining after repository and output are removed. Treat quoted strings as a single instruction block.
- render stack: triggered by keywords like
render,mkdocs,vitepress,build site,static site. Mapmkdocs/vitepress/bothdirectly. The word "render" alone (without a named stack) should be clarified with the user before defaulting — do not silently pick a stack. - serve: triggered by
serve,preview,open in browser,live preview. If a port number appears nearby (e.g. "on 3000"), use it; otherwise omit the port and letrender_docs.shdefault to 8000. Serving implies--renderis also set — if--serveis requested but no stack is named, ask the user which stack to render.
2. Present a structured confirmation overview
Render the parsed options back to the user in a compact block before doing anything. Example:
╭─ codewiki — parameters ──────────────────────────────╮
│ Repository : anthropics/claude-code │
│ (expanded) : https://github.com/anthropics/ │
│ claude-code.git │
│ Output dir : . │
│ Instructions : "Focus on the auth module; skip │
│ vendored code." │
│ Render stack : both │
│ Serve : on, port 3000 │
╰──────────────────────────────────────────────────────╯
If a field was inferred from natural language (not stated literally), mark it
with (inferred) so the user can correct it. If Serve is on, always show
the URLs that will be served (http://localhost:PORT for mkdocs,
http://localhost:PORT+1 for vitepress when --render both) so the user
knows what to expect.
3. Prompt for confirmation or modification (STRICT)
Present exactly two actionable paths. Do not run the script yet.
Confirm to execute, or tell me what to change.
- Reply
yes/confirm/go→ I will run:./scripts/codewiki.sh -r anthropics/claude-code \ -o . \ -i "Focus on the auth module; skip vendored code." \ --render both \ --serve 3000- Reply
modify: <field> = <value>→ I will update the parameter table and re-prompt.- Reply
cancel→ abort without side effects.
4. Execute (only after confirmation)
Run the underlying script with the exact flags agreed above. Stream its output to the conversation. On completion, report:
- The path to the generated wiki (typically
<output>/<repo>/wiki). - The paths to any rendered static sites
(
<output>/<repo>/mkdocs/site,<output>/<repo>/vitepress/site). - The preview URLs if
--servewas used. - Any warnings from
codewikiorrender_docs.shworth the user's attention.
If --serve was used, the script blocks in the foreground serving HTTP.
Tell the user explicitly to press Ctrl-C when done previewing — the
cleanup trap will tear down the server(s) automatically.
Hard rules
- Never run
codewiki.shbefore the user confirms. This skill clones remote repositories — that is a side effect with network and disk cost. Rendering and serving add further disk and long-running process side effects. - Never invent a repository when none was provided. If parsing yields no repository, ask the user for one.
- Never silently pick a render stack. If the user says "render" but
does not name
mkdocs/vitepress/both, ask which stack they want. - Never start
--servewithout--render. The script will reject this with exit code 1, but call it out during parsing so the user is not surprised. - Always show the expanded clone URL when the user supplied a shorthand
group/repoform, so they can verify the target before cloning. - Always show which ports will be opened when
--serveis used. - Preserve instruction text verbatim. Do not reword, summarize, or trim
it before passing it to
-i.
Top skills in this category
Humanizer
@biostartechnologyRemove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Elite Longterm Memory
@nextfrontierbuildsUltimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Model Usage
@steipeteUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Screenshot
@ivangdavilaCapture, inspect, and compare screenshots of screens, windows, regions, web pages, simulators, and CI runs with the right tool, wait strategy, viewport, and...
Interview Simulator
@wscatsSimulates mock interviews for any role and experience level with tailored technical, behavioral, and case questions plus detailed feedback and scoring.